Abstract:
:Accurate medical image segmentation is essential for diagnosis and treatment planning of diseases. Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they are still challenged by complicated conditions where the segmentation target has large variations of position, shape and scale, and existing CNNs have a poor explainability that limits their application to clinical decisions. In this work, we make extensive use of multiple attentions in a CNN architecture and propose a comprehensive attention-based CNN (CA-Net) for more accurate and explainable medical image segmentation that is aware of the most important spatial positions, channels and scales at the same time. In particular, we first propose a joint spatial attention module to make the network focus more on the foreground region. Then, a novel channel attention module is proposed to adaptively recalibrate channel-wise feature responses and highlight the most relevant feature channels. Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object. Extensive experiments on skin lesion segmentation from ISIC 2018 and multi-class segmentation of fetal MRI found that our proposed CA-Net significantly improved the average segmentation Dice score from 87.77% to 92.08% for skin lesion, 84.79% to 87.08% for the placenta and 93.20% to 95.88% for the fetal brain respectively compared with U-Net. It reduced the model size to around 15 times smaller with close or even better accuracy compared with state-of-the-art DeepLabv3+. In addition, it has a much higher explainability than existing networks by visualizing the attention weight maps. Our code is available at https://github.com/HiLab-git/CA-Net.
journal_name
IEEE Trans Med Imagingjournal_title
IEEE transactions on medical imagingauthors
Gu R,Wang G,Song T,Huang R,Aertsen M,Deprest J,Ourselin S,Vercauteren T,Zhang Sdoi
10.1109/TMI.2020.3035253subject
Has Abstractpub_date
2020-11-02 00:00:00eissn
0278-0062issn
1558-254Xjournal_volume
PPpub_type
杂志文章abstract::A novel framework for the classification of acute rejection versus nonrejection status of renal transplants from 2-D dynamic contrast-enhanced magnetic resonance imaging is proposed. The framework consists of four steps. First, kidney objects are segmented from adjacent structures with a level set deformable boundary ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2013.2269139
更新日期:2013-10-01 00:00:00
abstract::True three-dimensional (3-D) volume reconstruction from fully 3-D data in positron emission tomography (PET) has only a limited clinical use because of its large computational burden. Fourier rebinning (FORE) of the fully 3-D data into a set of 2-D sinogram data decomposes the 3-D reconstruction process into multiple ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.870257
更新日期:2000-05-01 00:00:00
abstract::Component averaging (CAV) was recently introduced by Censor, Gordon, and Gordon as a new iterative parallel technique suitable for large and sparse unstructured systems of linear equations. Based on earlier work of Byrne and Censor, it uses diagonal weighting matrices, with pixel-related weights determined by the spar...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.959302
更新日期:2001-10-01 00:00:00
abstract::Prostate cancer (PCa) recurrences are often predicted by assessing the status of surgical margins (SM)- positive surgical margins (PSM) increase the chances of biochemical recurrence by 2-4 times which may lead to PCa recurrence. To this end, an electrical impedance acquisition system with a microendoscopic probe was ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2016.2578939
更新日期:2016-12-01 00:00:00
abstract::Fast magnetic resonance imaging slice acquisition techniques such as single shot fast spin echo are routinely used in the presence of uncontrollable motion. These techniques are widely used for fetal magnetic resonance imaging (MRI) and MRI of moving subjects and organs. Although high-quality slices are frequently acq...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2010.2051680
更新日期:2010-10-01 00:00:00
abstract::Coronary artery disease is a major cause of death in women. Breast arterial calcifications (BACs), detected inmammograms, can be useful riskmarkers associated with the disease. We investigate the feasibility of automated and accurate detection ofBACsinmammograms for risk assessment of coronary artery disease. We devel...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2017.2655486
更新日期:2017-05-01 00:00:00
abstract::In this paper, we are interested in soft tissue differentiation by multiband images obtained from the High-Resolution Ultrasonic Transmission Tomography (HUTT) system using a spectral target detection method based on constrained energy minimization (CEM). We have developed a new tissue differentiation method (called "...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/tmi.2004.843179
更新日期:2005-03-01 00:00:00
abstract::A fully automated 2-D+time myocardial segmentation framework is proposed for cardiac magnetic resonance (CMR) blood-oxygen-level-dependent (BOLD) data sets. Ischemia detection with CINE BOLD CMR relies on spatio-temporal patterns in myocardial intensity, but these patterns also trouble supervised segmentation methods,...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2017.2726112
更新日期:2017-11-01 00:00:00
abstract::Image interpolation is an important operation that is widely used in medical imaging, image processing, and computer graphics. A variety of interpolation methods are available in the literature. However, their systematic evaluation is lacking. In a previous paper, we presented a framework for the task-independent comp...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.759116
更新日期:1999-02-01 00:00:00
abstract::A noninvasive computer-aided-theragnosis (CAT) system was developed for the early therapeutic cancer response assessment in patients with locally advanced breast cancer (LABC) treated with neoadjuvant chemotherapy. The proposed CAT system was based on multi-parametric quantitative ultrasound (QUS) spectroscopic method...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2015.2495246
更新日期:2016-03-01 00:00:00
abstract::Computerized detection of clustered microcalcifications (MCs) in mammograms often suffers from the occurrence of false positives (FPs), which can vary greatly from case to case. We investigate how to apply statistical estimation to determine the number of FPs that are present in a detected MC lesion. First, we describ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2017.2654799
更新日期:2017-05-01 00:00:00
abstract::In dynamic planar imaging, extraction of signals specific to structures is complicated by structures superposition. Due to overlapping, signals extraction with classic regions of interest (ROIs) methods suffers from inaccuracy, as extracted signals are a mixture of targeted signals. Partial volume effect raises the sa...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2017.2759661
更新日期:2018-01-01 00:00:00
abstract::An automatic method has been developed for segmentation of abdominal computed tomography (CT) images for virtual colonoscopy obtained after a bowel preparation of a low-residue diet with ingested contrast solutions to enhance the image intensities of residual colonic materials. Removal of the enhanced materials was pe...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.897814
更新日期:2000-12-01 00:00:00
abstract::The purpose of this study is to develop and test a new computerized model for predicting near-term breast cancer risk based on quantitative assessment of bilateral mammographic image feature variations in a series of negative full-field digital mammography (FFDM) images. The retrospective dataset included series of fo...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2016.2527619
更新日期:2016-07-01 00:00:00
abstract::A software system, CTIP, written in Fortran is discussed which remaps the computerized tomography (CT) image gray level so that both the lung and heart regions are clearly visible with a "natural anatomical appearance." The system is adaptive to image statistics derived from the gray-level histogram of the entire imag...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.1986.4307736
更新日期:1986-01-01 00:00:00
abstract::In this paper, the accuracy of material decomposition (MD) using an energy discriminating photon counting detector was studied. An MD framework was established and validated using calcium hydroxyapatite (CaHA) inserts of known densities (50 mg/cm3, 100 mg/cm3, 250 mg/cm3, 400 mg/cm3), and diameters (1.2, 3.0, and 5.0 ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2914370
更新日期:2020-01-01 00:00:00
abstract::Dynamic contrast-enhanced magnetic resonance (DCE-MR) imaging can be used to study microvascular structure in vivo by monitoring the abundance of an injected diffusible contrast agent over time. The resulting spatially resolved intensity-time curves are usually interpreted in terms of kinetic parameters obtained by fi...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2009.2019957
更新日期:2009-10-01 00:00:00
abstract::Diffuse optical tomography (DOT) is a noninvasive technique which measures hemodynamic changes in the tissue with near infrared light, which has been increasingly used to study brain functions. Due to the nature of light propagation in the tissue, the reconstruction problem is severely ill-posed. For linearized DOT pr...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2014.2338214
更新日期:2014-12-01 00:00:00
abstract::Accurate localization of the optic radiation is key to improving the surgical outcome for patients undergoing anterior temporal lobe resection for the treatment of refractory focal epilepsy. Current commercial interventional magnetic resonance imaging (MRI) scanners are capable of performing anatomical and diffusion w...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2011.2179668
更新日期:2012-04-01 00:00:00
abstract::Alzheimer's disease (AD) is a serious neurodegenerative condition that affects millions of individuals across the world. As the average age of individuals in the United States and the world increases, the prevalence of AD will continue to grow. To address this public health problem, the research community has develope...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2958943
更新日期:2020-06-01 00:00:00
abstract::Monitoring of cerebral diseases associated with a change of morphology (e.g., stroke) requires unprecedented accuracy for quantification of its morphological progression for each voxel. The purpose of this paper is to provide a technique [voxel-guided morphometry (VGM)] to quantify macroscopic anatomical differences. ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2002.806571
更新日期:2003-01-01 00:00:00
abstract::Segmentation of the wrist bones in CT images has been frequently used in different clinical applications including arthritis evaluation, bone age assessment and image-guided interventions. The major challenges include non-uniformity and spongy textures of the bone tissue as well as narrow inter-bone spaces. In this wo...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2016.2529500
更新日期:2016-08-01 00:00:00
abstract::Cone beam X-ray luminescence computed tomography (CB-XLCT) is a promising imaging technique in studying the physiological and pathological processes in small animals. However, the dynamic bio-distributions of probes in small animal, especially in adjacent targets are still hard to be captured directly from dynamic CB-...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2917026
更新日期:2019-12-01 00:00:00
abstract::This paper introduces and evaluates a block-iterative Fisher scoring (BFS) algorithm. The algorithm provides regularized estimation in tomographic models of projection data with Poisson variability. Regularization is achieved by penalized likelihood with a general quadratic penalty. Local convergence of the block-iter...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2008.918355
更新日期:2008-08-01 00:00:00
abstract::The effects of Squashing, an algorithm introduced by J.A. Reeds and L.A. Shepp (see ibid., vol.MI-6, no.2, p.89-97, June 1987), are described. It is proven that Squashing induces a weight function upon the projections. Intuitive and numerical evidence is presented showing that this weight function is not desirable at ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.57761
更新日期:1990-01-01 00:00:00
abstract::Nonrigid registration of medical images is important for a number of applications such as the creation of population averages, atlas-based segmentation, or geometric correction of functional magnetic resonance imaging (fMRI) images to name a few. In recent years, a number of methods have been proposed to solve this pr...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2003.819299
更新日期:2003-11-01 00:00:00
abstract::The response characteristics of two tomographic systems were compared for imaging of positron emitters: a) a SPECT system with a 3/8 in crystal and 511 keV detector shielding, equipped with a specially designed 511 keV collimator, and b) a PET V system using coincidence detection. SPECT transverse plane resolution was...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.1986.4307776
更新日期:1986-01-01 00:00:00
abstract::Two methods of rejecting pileup events in 2-D array detectors used in positron emission tomography (PET) are investigated. Since the methods are based on different physical properties, they were investigated separately and in combination. Method one is based on the fact that valid events in the 2-D array detector occu...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.79481
更新日期:1991-01-01 00:00:00
abstract::The most frequent extracranial solid tumors of childhood, named peripheral neuroblastic tumors (pNTs), are very challenging to diagnose due to their diversified categories and varying forms. Auxiliary diagnosis methods of such pediatric malignant cancers are highly needed to provide pathologists assistance and reduce ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2020.3027547
更新日期:2021-01-01 00:00:00
abstract::The identification of bronchi on Computed Tomography (CT) images of the lungs provides valuable clinical information in patients with suspected airways diseases including bronchiectasis, emphysema, or constrictive obliterative bronchiolitis. The automated recognition of the airways is, therefore, an important part of ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.952731
更新日期:2001-09-01 00:00:00